Prior Predictive Checks for the Method of Covariances in Bayesian Mediation Analysis

Zundert, Camiel Van; Somer, Emma; Miočević, Milica

doi:10.1080/10705511.2021.1977648

Cited by 5 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Close Replication: In the most constrained condition, factor loadings and thresholds were assigned Normal prior distributions with mean hyperparameters set to the corresponding 5 Herein, we demonstrate prior predictive similarity checking in the context of factor analysis, but the same methodology applies to other models. Readers who wish to extend this method to other models should consult our reading list (https://osf.io/q6rvf/) for relevant tutorials on prior specification and prior predictive model checking (e.g., van Zundert et al, 2022;Winter & Depaoli, 2023;Zondervan-Zwijnenburg et al, 2017). 6 We focused on prior specifications that are currently available in accessible software.…”

Section: Empirical Applicationmentioning

confidence: 99%

Good fit is weak evidence of replication: Increasing rigor through prior predictive similarity checking

Bonifay,

Winter,

Skoblow

et al. 2024

Preprint

View full text Add to dashboard Cite

Jerzy Neyman declared, “Models become plausible by repetition.” What he called repetition is now known as model replication and entails applying the same statistical model to data from different studies. Typically, researchers rely on goodness-of-fit – indexing the degree to which the model represents the data – as evidence of successful replication. But we demonstrate that goodness-of-fit testing fails to capture important (dis)similarities between studies. As an alternative, we propose prior predictive similarity checking: a method for rigorous comparison of the data patterns and/or model parameters from different studies. We illustrate this method using psychopathology data from the National Comorbidity Survey (NCS) and its purported replication, the NCS-R. Both data sets yielded excellent fit, but often failed to pass our more demanding similarity checking technique. We conclude with recommendations for applied model replication research.

show abstract

Section: Empirical Applicationmentioning

confidence: 99%